[Paper study] Delay learning and polychronization for reservoir computing
来源:互联网 发布:c 数组的长度 编辑:程序博客网 时间:2024/06/09 17:50
CNNs use spiking neural networks (SNNs) as its backbone. A SNN structure called reservoir and its learning algorithm “reservoir computing” (RC) is described in Paugam-Moisy et al. 2008. She adopted a multi-timescale learning algorithm, which use STDP in millisecond level (synapse level) and a supervised adaptation of axonal transmission delays toward readout neurons coding.
Here is the summary after studying this paper.
This is the network structure,
This is the STDP weight updating rule,
A multiplicative approach is adopted for weight updating where weights are updated as Wij = Wij + α * (Wij – Wmin) * ΔW, if ΔW <=0. And Wij = Wij + α * (Wmax – Wij) * ΔW, if ΔW >=0.
This is the SRM0 spiking neuron model,
This is the pseudo-code for supervised adaptive delays (the multi class version is analogical).
repeatfor each example X=(p, class) of the database{ present the input pattern p; define the target output neuron according to class; if (the target output neuron fires less than μms before the non-target one, or fires after it ) then { select one triggering connection of the target output neuron and decrement its delay (-1ms), except if dmin is reached already; select one triggering connection of the non-target output neuron and increment its delay (+1ms), except if dmax is reached already; }}until a given maximum learning time is over.
Note that the recognized pattern is represented by the first firing output neuron.
Simulations and visualization of the reservoir will follow in the future posts. Enjoy.
- [Paper study] Delay learning and polychronization for reservoir computing
- [Paper Study] Polychronization: Computation with Spikes
- #Paper Reading# Lifelong Machine Learning for Topic Modeling and Beyond
- Reservoir Computing简介
- Reservoir Computing简介
- english study and learning materials
- [Paper note] Joint Learning of Single-image and Cross-image Representations for Person Re-id.
- Learning to Hash Paper, Code and Dataset
- #Paper Reading# Lifelong Learning for Sentiment Classification
- #Paper Reading# Dual Learning for Machine Translation
- [Paper Study] Fundamentals in Spike Response Model and SpikeProp
- Grid Computing for Bioinformatics and Computational Biology
- Position Paper For the Workshop on Web of Services for Enterprise Computing
- [读PAPER]Online Unsupervised Feature Learning for Visual Tracking
- Paper Reading 4:Massively Parallel Methods for Deep Reinforcement Learning
- paper: cvprw2015deep learning of binary hash for fast retrieval
- #Paper Reading# Toward an Architecture for Never-Ending Language Learning
- #Paper Reading# Active Task Selection for Lifelong Machine Learning
- WSO2 ESB 学习(二) ---安装篇
- Ruby实现单例模式
- 教你如何迅速秒杀掉:99%的海量数据处理面试题
- poj-2029-Get Many Persimmon Trees-预处理
- SDL-第一课“hello world”
- [Paper study] Delay learning and polychronization for reservoir computing
- JAVA设计模式之观察者模式2
- intel 64 and IA-32 Archtectures Software Developer's Manual 笔记
- 图像处理--角点检测(Harris以及其他算法研究)
- Android-Linux
- 浏览器窗口被激活
- 黑马程序员-----java基础:面向对象与单例设计模式
- WARNING: gnome-keyring:: couldn't connect to
- PHP实践之路(三)PHP初探数据类型